From 9573b48253e721ff392a0bad67a67492d8a14bfe Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 4 Nov 2024 10:59:42 +0100
Subject: [PATCH] Data updates for obo-db-ingest (#1252)

This PR makes several minor updates to support making a new output of
https://github.com/biopragmatics/obo-db-ingest

1. Extend CDDS pattern to allow for unversioned records (i.e., not
ending with `\.\d+`
2. Extend COSMIC pattern to allow for dashes
3. Add ability to encode 3.4.24.B15 in EC (see
https://www.brenda-enzymes.org/enzyme.php?ecno=3.4.24.B15)
4. Add second letter in MEROPS entry so XM02.001 can be encoded (the M
was the issue). This appears in HGNC gene cross-references.
---
 src/bioregistry/constants.py          |  2 ++
 src/bioregistry/data/bioregistry.json | 17 +++++++++++++----
 2 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/src/bioregistry/constants.py b/src/bioregistry/constants.py
index 6041ab787..a4a10da73 100644
--- a/src/bioregistry/constants.py
+++ b/src/bioregistry/constants.py
@@ -130,6 +130,8 @@
     "pid.pathway",
     # this uses namespace-in-namespace
     "neurolex",
+    # Miriam needs to be extended
+    "ccds",
 }
 IDENTIFIERS_ORG_URL_PREFIX = "https://identifiers.org/"
 
diff --git a/src/bioregistry/data/bioregistry.json b/src/bioregistry/data/bioregistry.json
index b38d2b15c..c7aface95 100644
--- a/src/bioregistry/data/bioregistry.json
+++ b/src/bioregistry/data/bioregistry.json
@@ -13045,6 +13045,10 @@
       "name": "Terence D. Murphy",
       "orcid": "0000-0001-9311-9745"
     },
+    "example": "CCDS12976",
+    "example_extras": [
+      "CCDS12976.1"
+    ],
     "fairsharing": {
       "abbreviation": "CCDS",
       "description": "The Consensus CDS (CCDS) project is a collaborative effort to identify a core set of human and mouse protein coding regions that are consistently annotated and of high quality. The long term goal is to support convergence towards a standard set of gene annotations.",
@@ -13115,6 +13119,7 @@
       "prefix": "ccds",
       "uri_format": "http://www.ncbi.nlm.nih.gov/CCDS/CcdsBrowse.cgi?REQUEST=CCDS&DATA=$1"
     },
+    "pattern": "^CCDS\\d+(\\.\\d+)?$",
     "prefixcommons": {
       "description": "The Consensus CDS (CCDS) project is a collaborative effort to identify a core set of human and mouse protein coding regions that are consistently annotated and of high quality. The long term goal is to support convergence towards a standard set of gene annotations.",
       "example": "4824",
@@ -21794,6 +21799,7 @@
       "prefix": "Cosmic",
       "uri_format": "https://cancer.sanger.ac.uk/cosmic/sample/overview?id=$1"
     },
+    "comment": "Is this just HGNC Gene symbols?",
     "contact": {
       "email": "jt6@sanger.ac.uk",
       "github": "jgtate",
@@ -21869,6 +21875,7 @@
       "prefix": "cosmic",
       "uri_format": "http://cancer.sanger.ac.uk/cosmic/gene/overview?ln=$1"
     },
+    "pattern": "^[A-Z0-9][A-Z0-9-]*$",
     "publications": [
       {
         "doi": "10.1093/nar/gky1015",
@@ -30210,7 +30217,8 @@
       "2.3",
       "2.3.1",
       "2.3.1.n12",
-      "3.1.26.n2"
+      "3.1.26.n2",
+      "3.4.24.B15"
     ],
     "fairsharing": {
       "abbreviation": "EC Number",
@@ -30322,7 +30330,7 @@
       "name": "Integrated relational Enzyme database",
       "prefix": "106"
     },
-    "pattern": "^\\d{1,2}(((\\.\\d{1,3}){1,3})|(\\.\\d+){2}\\.n\\d{1,3})?$",
+    "pattern": "^\\d{1,2}(((\\.\\d{1,3}){1,3})|(\\.\\d+){2}\\.[nB]\\d{1,3})?$",
     "prefixcommons": {
       "description": "IntEnz is a freely available resource focused on enzyme nomenclature. IntEnz contains the recommendations of the Nomenclature Committee of the International Union of Biochemistry and Molecular Biology (NC-IUBMB) on the nomenclature and classification of enzyme-catalysed reactions.",
       "example": "17854",
@@ -65185,7 +65193,8 @@
     },
     "example": "I31.952",
     "example_extras": [
-      "S01.001"
+      "S01.001",
+      "XM02.001"
     ],
     "fairsharing": {
       "abbreviation": "MEROPS",
@@ -65273,7 +65282,7 @@
       "uri_format": "http://merops.sanger.ac.uk/cgi-bin/pepsum?id=$1"
     },
     "name": "MEROPS Entry",
-    "pattern": "^[SCTAGMNUI]\\d{2}\\.([AB]\\d{2}|\\d{3})$",
+    "pattern": "^[SCTAGMNUIX]{1,2}\\d{2}\\.([AB]\\d{2}|\\d{3})$",
     "prefixcommons": {
       "description": "The MEROPS database is an information resource for peptidases (also termed proteases, proteinases and proteolytic enzymes) and the proteins that inhibit them.",
       "example": "S01.001",